arxiv
PublishedMay 22, 2026 at 4:00 AM
MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents
Publisher summary· verbatim
arXiv:2604.15774v2 Announce Type: replace Abstract: Equipping Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks. Specifically, contaminated or biased memory accumulation can trigger abnormal agent behaviors. Existi
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivGAGPO: Generalized Advantage Grouped Policy Optimization3harxivUP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems3harxivOrchestra-o1: Omnimodal Agent Orchestration3harxivHybrid Open-Ended Tri-Evolution Makes Better Deep Researcher3hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗